266 commits

Author	SHA1	Message	Date
leeetao	42da179d66	Added parameter display for the distilled model of deepseek-qwen	2025-02-24 13:24:56 +00:00
leeetao	7bf1b743fb	Merge branch 'dev' into lt_test ... Merge dev branch updates into local branch lt_test.	2025-02-23 08:35:45 +00:00
leeetao	f99e08b9fe	Added inference support for the Deepseek distilled model	2025-02-23 08:27:37 +00:00
Lizonghang	e219fada4e	disable timer	2025-02-19 16:24:12 +04:00
Lizonghang	c84f9d29fe	use arg prefetch and remove arg unload	2025-02-12 17:04:41 +04:00
Lizonghang	708b1d8c89	disable force fetching	2025-02-12 16:55:44 +04:00
Lizonghang	ea0e655a8b	disable force feteching	2025-02-12 16:55:21 +04:00
Lizonghang	b163918b46	disable prefetch in standalone mode	2025-02-12 00:17:33 +04:00
Lizonghang	6a50d494d2	increase prefetch dense	2025-02-11 17:25:06 +04:00
Lizonghang	65ad14140a	do not check loaded tensors due to increased latency	2025-02-11 17:10:11 +04:00
Lizonghang	3dd3138207	ignore tensors already in page cache when prefetching	2025-02-11 17:00:17 +04:00
Zonghang Li	261c88f058	skip tensors on CUDA in manage_graph_tensors	2025-02-11 09:49:17 +04:00
Zonghang Li	c4c6a642fc	manage_graph_tensors: fix segment prefetch	2025-02-08 22:44:38 +04:00
Lizonghang	8e41362af0	fix prefetch	2025-02-04 17:38:41 +04:00
Lizonghang	215151918f	fix gpu mem limit	2025-01-31 18:52:13 +04:00
Lizonghang	17cd8ba618	reverse 300MiB for Metal kernel	2025-01-31 16:24:44 +04:00
Lizonghang	dd632ee6df	ignore the first 5 evals due to preheat	2025-01-31 08:53:51 +04:00
Lizonghang	b680cb74fe	set POSIX_MADV_WILLNEED for the next subgraph	2025-01-30 13:29:34 +04:00
Lizonghang	f9b4c46b74	ignore the first eval to make time test more accurate	2025-01-30 11:12:26 +04:00
Lizonghang	849b47ccd0	fix auto schedule logic	2025-01-29 13:13:37 +04:00
Lizonghang	631daadd92	test	2025-01-28 16:36:47 +04:00
Lizonghang	2934cf3e8e	reserve 200 mib for internal gpu usage	2025-01-27 22:14:12 +04:00
Lizonghang	1ca9a43bd1	keep the output layer weights in shared memory by default	2025-01-25 23:31:43 +04:00
Lizonghang	f3dd5776eb	fix kappa and memory bounds, account for look-up table and input/output layer delay	2025-01-25 22:31:40 +04:00
Lizonghang	1c0087e919	rename arg --keep-inp-out-in-metal to --keep-out-in-metal	2025-01-23 23:17:06 +04:00
Lizonghang	fb05f80f89	remove token_embd from metal mem	2025-01-23 16:58:25 +04:00
Lizonghang	78a544d716	add metal mem limit	2025-01-23 16:08:52 +04:00
Zonghang Li	33429ec4e1	add option --keep-inp-out-in-metal	2025-01-22 11:25:09 +04:00
Lizonghang	facb4ea736	add option --keep-inp-out-in-metal and fix bugs in unmap	2025-01-22 11:15:19 +04:00
Lizonghang	ce2ef9699f	fix mapping unmap_fragment error	2025-01-21 22:43:51 +04:00
Lizonghang	189ed92cba	segment mmap range on Metal shared memory to avoid memory waste	2025-01-21 21:07:02 +04:00
Lizonghang	e7fae2acdb	fix cuda mem limitation	2025-01-16 09:48:08 +04:00
Zonghang Li	46e99218b4	add arg --cuda-mem	2025-01-16 09:15:34 +04:00
Lizonghang	1e1ba5bb91	add api llama_model_set_n_gpu_layers	2025-01-15 10:47:53 +04:00
Lizonghang	9279a2e3ff	fix error in llama_context_n_gpu_layers	2025-01-15 10:08:41 +04:00
Lizonghang	5d9aadf3d5	use highs to solve the allocation program	2025-01-15 10:04:04 +04:00
Zonghang Li	0b9720c222	modify default max nodes back to 8192	2025-01-04 19:18:59 +04:00
Zonghang Li	e543fcd55f	fix buf_compute_meta size	2025-01-04 19:16:38 +04:00
Zonghang Li	b2f806a572	increase default max nodes from 8192 to 16384	2025-01-04 11:08:35 +04:00
Zonghang Li	b712ad3044	fix flops test error	2024-12-31 09:37:46 +04:00
Lizonghang	fa31ca8e35	add os detect	2024-12-30 09:13:12 +04:00
Lizonghang	a7ec685eda	add memcpy speed test	2024-12-29 16:19:08 +04:00
Lizonghang	b642d70188	fix swappable mem in termux	2024-12-12 15:15:16 +04:00
Lizonghang	8e9ab45458	fix model bytes counter	2024-12-10 14:57:48 +04:00
Lizonghang	d78fa427e7	add memory copy speed test	2024-12-09 10:07:42 +04:00
Lizonghang	2c2171cebf	fix display	2024-12-08 22:57:12 +04:00
Zonghang Li	df813675d0	fix flops count and ram/vram speed test	2024-12-08 10:14:05 +04:00
Lizonghang	cd823546dd	llama_profile_device: add arg n_predict	2024-12-06 16:37:25 +04:00
Lizonghang	a46d56cc60	llama_model_n_flops: remove ctxs	2024-12-06 11:31:53 +04:00
Lizonghang	f1c1d1b929	add support for Q5_K and fix byte count for Q6_K	2024-12-06 07:59:45 +04:00